create_flow

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a non-idempotent mutation (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false). The description adds a meaningful constraint beyond that — steps must correspond to observed recorded actions, not fabricated navigation — but says nothing about validation failure behavior, duplicate handling, or limits (max 30 steps).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core action and followed by the key semantic constraint about observed vs invented steps. No filler, though it is arguably under-sized for a 5-parameter mutation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A mutating tool with 5 undocumented parameters, a nested steps array with required recordingId/label, no output schema, and no annotation detail beyond hints. The description omits what is created/returned (e.g., a flow id), required-vs-optional fields, and the 30-step cap — significant gaps for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, so the description carries the full burden and largely fails: title, platform (ios/android enum), tags, appId, and the steps sub-fields (startMs/endMs/action) get no explanation. Only the implicit link from steps to existing recordings is conveyed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Store') and resource ('an ordered reference journey') and clarifies the nature of the object — a flow assembled from existing recordings rather than an invented trace. It is distinguishable from get_flow (read counterpart) without opening schemas, though the sibling relationship is never named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies the prerequisite that recordings must already exist locally ('backed by existing local recordings'), which guides the agent to import_recording/list_recordings first. However, it never states when to use this versus get_flow or what happens if the referenced recordings don't exist, so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.